Identifying Failure Root Causes for Cloud-Native Microservice Applications
Bibliographic record
Abstract
Cloud-native microservice applications depend on reliable platforms to ensure stable performance, even under resource overload faults. However, understanding the root causes of system failures holistically remains a significant challenge. This paper proposes a novel, root cause-oriented framework that supports autonomic, self-managing systems with humans in the loop. Our approach leverages a three-fold modality of observability data—logs, metrics, and traces—to build a multi-perspective view of system behavior. We enhance preprocessing to extract metric anomaly scores and log semantics (e.g., Template ID counts and Golden Signal counts), which are then fused to train a GNN-GRU model. This model captures spatial and temporal patterns across services to classify failure types and identify the root causes behind them. The resulting root cause predictions—including correlated anomalies and their associated source and target services—are analyzed to provide context-rich insights, aiding human operators (e.g., SREs) in debugging and diagnosis. Our framework fits naturally into the Monitor-Analyze-Plan-Execute (MAPE) loop, enabling proactive fault management and feedback-driven improvement. Evaluations using the public MicroSS dataset—comprising faults like resource saturation and configuration errors—demonstrate the effectiveness of our method in accurately identifying failure origins and supporting operational resilience.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".